diff options
Diffstat (limited to 'arch/arm64/kernel')
-rw-r--r-- | arch/arm64/kernel/acpi.c | 2 | ||||
-rw-r--r-- | arch/arm64/kernel/armv8_deprecated.c | 3 | ||||
-rw-r--r-- | arch/arm64/kernel/cpu-reset.S | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/cpu_errata.c | 28 | ||||
-rw-r--r-- | arch/arm64/kernel/cpufeature.c | 191 | ||||
-rw-r--r-- | arch/arm64/kernel/cpuinfo.c | 9 | ||||
-rw-r--r-- | arch/arm64/kernel/entry-common.c | 8 | ||||
-rw-r--r-- | arch/arm64/kernel/entry.S | 28 | ||||
-rw-r--r-- | arch/arm64/kernel/fpsimd.c | 30 | ||||
-rw-r--r-- | arch/arm64/kernel/hibernate.c | 151 | ||||
-rw-r--r-- | arch/arm64/kernel/kaslr.c | 11 | ||||
-rw-r--r-- | arch/arm64/kernel/kexec_image.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/machine_kexec.c | 12 | ||||
-rw-r--r-- | arch/arm64/kernel/machine_kexec_file.c | 106 | ||||
-rw-r--r-- | arch/arm64/kernel/process.c | 12 | ||||
-rw-r--r-- | arch/arm64/kernel/ptrace.c | 21 | ||||
-rw-r--r-- | arch/arm64/kernel/setup.c | 10 | ||||
-rw-r--r-- | arch/arm64/kernel/signal.c | 6 | ||||
-rw-r--r-- | arch/arm64/kernel/signal32.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/ssbd.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/syscall.c | 4 | ||||
-rw-r--r-- | arch/arm64/kernel/traps.c | 3 |
22 files changed, 485 insertions, 166 deletions
diff --git a/arch/arm64/kernel/acpi.c b/arch/arm64/kernel/acpi.c index 3a58e9db5cfe..a100483b47c4 100644 --- a/arch/arm64/kernel/acpi.c +++ b/arch/arm64/kernel/acpi.c @@ -274,7 +274,7 @@ int apei_claim_sea(struct pt_regs *regs) if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES)) return err; - current_flags = arch_local_save_flags(); + current_flags = local_daif_save_flags(); /* * SEA can interrupt SError, mask it and describe this as an NMI so diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index ca158be21f83..7832b3216370 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -618,7 +618,8 @@ static struct insn_emulation_ops setend_ops = { }; /* - * Invoked as late_initcall, since not needed before init spawned. + * Invoked as core_initcall, which guarantees that the instruction + * emulation is ready for userspace. */ static int __init armv8_deprecated_init(void) { diff --git a/arch/arm64/kernel/cpu-reset.S b/arch/arm64/kernel/cpu-reset.S index 6ea337d464c4..32c7bf858dd9 100644 --- a/arch/arm64/kernel/cpu-reset.S +++ b/arch/arm64/kernel/cpu-reset.S @@ -42,11 +42,11 @@ ENTRY(__cpu_soft_restart) mov x0, #HVC_SOFT_RESTART hvc #0 // no return -1: mov x18, x1 // entry +1: mov x8, x1 // entry mov x0, x2 // arg0 mov x1, x3 // arg1 mov x2, x4 // arg2 - br x18 + br x8 ENDPROC(__cpu_soft_restart) .popsection diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c index 6a09ca7644ea..703ad0a84f99 100644 --- a/arch/arm64/kernel/cpu_errata.c +++ b/arch/arm64/kernel/cpu_errata.c @@ -547,6 +547,9 @@ static const struct midr_range spectre_v2_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), + MIDR_ALL_VERSIONS(MIDR_HISI_TSV110), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_3XX_SILVER), + MIDR_ALL_VERSIONS(MIDR_QCOM_KRYO_4XX_SILVER), { /* sentinel */ } }; @@ -756,6 +759,20 @@ static const struct arm64_cpu_capabilities erratum_843419_list[] = { }; #endif +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE +static const struct midr_range erratum_speculative_at_vhe_list[] = { +#ifdef CONFIG_ARM64_ERRATUM_1165522 + /* Cortex A76 r0p0 to r2p0 */ + MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), +#endif +#ifdef CONFIG_ARM64_ERRATUM_1530923 + /* Cortex A55 r0p0 to r2p0 */ + MIDR_RANGE(MIDR_CORTEX_A55, 0, 0, 2, 0), +#endif + {}, +}; +#endif + const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE { @@ -882,12 +899,11 @@ const struct arm64_cpu_capabilities arm64_errata[] = { ERRATA_MIDR_RANGE_LIST(erratum_1418040_list), }, #endif -#ifdef CONFIG_ARM64_ERRATUM_1165522 +#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_AT_VHE { - /* Cortex-A76 r0p0 to r2p0 */ - .desc = "ARM erratum 1165522", - .capability = ARM64_WORKAROUND_1165522, - ERRATA_MIDR_RANGE(MIDR_CORTEX_A76, 0, 0, 2, 0), + .desc = "ARM errata 1165522, 1530923", + .capability = ARM64_WORKAROUND_SPECULATIVE_AT_VHE, + ERRATA_MIDR_RANGE_LIST(erratum_speculative_at_vhe_list), }, #endif #ifdef CONFIG_ARM64_ERRATUM_1463225 @@ -924,7 +940,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = { #ifdef CONFIG_ARM64_ERRATUM_1319367 { .desc = "ARM erratum 1319367", - .capability = ARM64_WORKAROUND_1319367, + .capability = ARM64_WORKAROUND_SPECULATIVE_AT_NVHE, ERRATA_MIDR_RANGE_LIST(ca57_a72), }, #endif diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 04cf64e9f0c9..0b6715625cf6 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -32,9 +32,7 @@ static unsigned long elf_hwcap __read_mostly; #define COMPAT_ELF_HWCAP_DEFAULT \ (COMPAT_HWCAP_HALF|COMPAT_HWCAP_THUMB|\ COMPAT_HWCAP_FAST_MULT|COMPAT_HWCAP_EDSP|\ - COMPAT_HWCAP_TLS|COMPAT_HWCAP_VFP|\ - COMPAT_HWCAP_VFPv3|COMPAT_HWCAP_VFPv4|\ - COMPAT_HWCAP_NEON|COMPAT_HWCAP_IDIV|\ + COMPAT_HWCAP_TLS|COMPAT_HWCAP_IDIV|\ COMPAT_HWCAP_LPAE) unsigned int compat_elf_hwcap __read_mostly = COMPAT_ELF_HWCAP_DEFAULT; unsigned int compat_elf_hwcap2 __read_mostly; @@ -47,19 +45,23 @@ static struct arm64_cpu_capabilities const __ro_after_init *cpu_hwcaps_ptrs[ARM6 /* Need also bit for ARM64_CB_PATCH */ DECLARE_BITMAP(boot_capabilities, ARM64_NPATCHABLE); +bool arm64_use_ng_mappings = false; +EXPORT_SYMBOL(arm64_use_ng_mappings); + /* * Flag to indicate if we have computed the system wide * capabilities based on the boot time active CPUs. This * will be used to determine if a new booting CPU should * go through the verification process to make sure that it * supports the system capabilities, without using a hotplug - * notifier. + * notifier. This is also used to decide if we could use + * the fast path for checking constant CPU caps. */ -static bool sys_caps_initialised; - -static inline void set_sys_caps_initialised(void) +DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); +EXPORT_SYMBOL(arm64_const_caps_ready); +static inline void finalize_system_capabilities(void) { - sys_caps_initialised = true; + static_branch_enable(&arm64_const_caps_ready); } static int dump_cpu_hwcaps(struct notifier_block *self, unsigned long v, void *p) @@ -119,6 +121,7 @@ static void cpu_enable_cnp(struct arm64_cpu_capabilities const *cap); * sync with the documentation of the CPU feature register ABI. */ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_RNDR_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_TS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_FHM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR0_DP_SHIFT, 4, 0), @@ -135,6 +138,10 @@ static const struct arm64_ftr_bits ftr_id_aa64isar0[] = { }; static const struct arm64_ftr_bits ftr_id_aa64isar1[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_DGH_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SPECRES_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_SB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR1_FRINTTS_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH), @@ -177,10 +184,18 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F64MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_F32MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), + FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE), FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), @@ -225,6 +240,7 @@ static const struct arm64_ftr_bits ftr_id_aa64mmfr1[] = { }; static const struct arm64_ftr_bits ftr_id_aa64mmfr2[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_E0PD_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_FWB_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_AT_SHIFT, 4, 0), ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64MMFR2_LVA_SHIFT, 4, 0), @@ -313,6 +329,17 @@ static const struct arm64_ftr_bits ftr_id_mmfr4[] = { ARM64_FTR_END, }; +static const struct arm64_ftr_bits ftr_id_isar6[] = { + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_I8MM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_BF16_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SPECRES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_SB_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_FHM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_DP_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, ID_ISAR6_JSCVT_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_pfr0[] = { ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 12, 4, 0), /* State3 */ ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_LOWER_SAFE, 8, 4, 0), /* State2 */ @@ -396,6 +423,7 @@ static const struct __ftr_reg_entry { ARM64_FTR_REG(SYS_ID_ISAR4_EL1, ftr_generic_32bits), ARM64_FTR_REG(SYS_ID_ISAR5_EL1, ftr_id_isar5), ARM64_FTR_REG(SYS_ID_MMFR4_EL1, ftr_id_mmfr4), + ARM64_FTR_REG(SYS_ID_ISAR6_EL1, ftr_id_isar6), /* Op1 = 0, CRn = 0, CRm = 3 */ ARM64_FTR_REG(SYS_MVFR0_EL1, ftr_generic_32bits), @@ -600,6 +628,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info) init_cpu_ftr_reg(SYS_ID_ISAR3_EL1, info->reg_id_isar3); init_cpu_ftr_reg(SYS_ID_ISAR4_EL1, info->reg_id_isar4); init_cpu_ftr_reg(SYS_ID_ISAR5_EL1, info->reg_id_isar5); + init_cpu_ftr_reg(SYS_ID_ISAR6_EL1, info->reg_id_isar6); init_cpu_ftr_reg(SYS_ID_MMFR0_EL1, info->reg_id_mmfr0); init_cpu_ftr_reg(SYS_ID_MMFR1_EL1, info->reg_id_mmfr1); init_cpu_ftr_reg(SYS_ID_MMFR2_EL1, info->reg_id_mmfr2); @@ -753,6 +782,8 @@ void update_cpu_features(int cpu, info->reg_id_isar4, boot->reg_id_isar4); taint |= check_update_ftr_reg(SYS_ID_ISAR5_EL1, cpu, info->reg_id_isar5, boot->reg_id_isar5); + taint |= check_update_ftr_reg(SYS_ID_ISAR6_EL1, cpu, + info->reg_id_isar6, boot->reg_id_isar6); /* * Regardless of the value of the AuxReg field, the AIFSR, ADFSR, and @@ -785,7 +816,7 @@ void update_cpu_features(int cpu, /* Probe vector lengths, unless we already gave up on SVE */ if (id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) && - !sys_caps_initialised) + !system_capabilities_finalized()) sve_update_vq_map(); } @@ -831,6 +862,7 @@ static u64 __read_sysreg_by_encoding(u32 sys_id) read_sysreg_case(SYS_ID_ISAR3_EL1); read_sysreg_case(SYS_ID_ISAR4_EL1); read_sysreg_case(SYS_ID_ISAR5_EL1); + read_sysreg_case(SYS_ID_ISAR6_EL1); read_sysreg_case(SYS_MVFR0_EL1); read_sysreg_case(SYS_MVFR1_EL1); read_sysreg_case(SYS_MVFR2_EL1); @@ -965,6 +997,46 @@ has_useable_cnp(const struct arm64_cpu_capabilities *entry, int scope) return has_cpuid_feature(entry, scope); } +/* + * This check is triggered during the early boot before the cpufeature + * is initialised. Checking the status on the local CPU allows the boot + * CPU to detect the need for non-global mappings and thus avoiding a + * pagetable re-write after all the CPUs are booted. This check will be + * anyway run on individual CPUs, allowing us to get the consistent + * state once the SMP CPUs are up and thus make the switch to non-global + * mappings if required. + */ +bool kaslr_requires_kpti(void) +{ + if (!IS_ENABLED(CONFIG_RANDOMIZE_BASE)) + return false; + + /* + * E0PD does a similar job to KPTI so can be used instead + * where available. + */ + if (IS_ENABLED(CONFIG_ARM64_E0PD)) { + u64 mmfr2 = read_sysreg_s(SYS_ID_AA64MMFR2_EL1); + if (cpuid_feature_extract_unsigned_field(mmfr2, + ID_AA64MMFR2_E0PD_SHIFT)) + return false; + } + + /* + * Systems affected by Cavium erratum 24756 are incompatible + * with KPTI. + */ + if (IS_ENABLED(CONFIG_CAVIUM_ERRATUM_27456)) { + extern const struct midr_range cavium_erratum_27456_cpus[]; + + if (is_midr_in_range_list(read_cpuid_id(), + cavium_erratum_27456_cpus)) + return false; + } + + return kaslr_offset() > 0; +} + static bool __meltdown_safe = true; static int __kpti_forced; /* 0: not forced, >0: forced on, <0: forced off */ @@ -975,6 +1047,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, static const struct midr_range kpti_safe_list[] = { MIDR_ALL_VERSIONS(MIDR_CAVIUM_THUNDERX2), MIDR_ALL_VERSIONS(MIDR_BRCM_VULCAN), + MIDR_ALL_VERSIONS(MIDR_BRAHMA_B53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A35), MIDR_ALL_VERSIONS(MIDR_CORTEX_A53), MIDR_ALL_VERSIONS(MIDR_CORTEX_A55), @@ -1008,7 +1081,7 @@ static bool unmap_kernel_at_el0(const struct arm64_cpu_capabilities *entry, } /* Useful for KASLR robustness */ - if (IS_ENABLED(CONFIG_RANDOMIZE_BASE) && kaslr_offset() > 0) { + if (kaslr_requires_kpti()) { if (!__kpti_forced) { str = "KASLR"; __kpti_forced = 1; @@ -1043,7 +1116,6 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) extern kpti_remap_fn idmap_kpti_install_ng_mappings; kpti_remap_fn *remap_fn; - static bool kpti_applied = false; int cpu = smp_processor_id(); /* @@ -1051,7 +1123,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) * it already or we have KASLR enabled and therefore have not * created any global mappings at all. */ - if (kpti_applied || kaslr_offset() > 0) + if (arm64_use_ng_mappings) return; remap_fn = (void *)__pa_symbol(idmap_kpti_install_ng_mappings); @@ -1061,7 +1133,7 @@ kpti_install_ng_mappings(const struct arm64_cpu_capabilities *__unused) cpu_uninstall_idmap(); if (!cpu) - kpti_applied = true; + arm64_use_ng_mappings = true; return; } @@ -1251,6 +1323,14 @@ static void cpu_enable_address_auth(struct arm64_cpu_capabilities const *cap) } #endif /* CONFIG_ARM64_PTR_AUTH */ +#ifdef CONFIG_ARM64_E0PD +static void cpu_enable_e0pd(struct arm64_cpu_capabilities const *cap) +{ + if (this_cpu_has_cap(ARM64_HAS_E0PD)) + sysreg_clear_set(tcr_el1, 0, TCR_E0PD1); +} +#endif /* CONFIG_ARM64_E0PD */ + #ifdef CONFIG_ARM64_PSEUDO_NMI static bool enable_pseudo_nmi; @@ -1291,7 +1371,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .cpu_enable = cpu_enable_pan, }, #endif /* CONFIG_ARM64_PAN */ -#if defined(CONFIG_AS_LSE) && defined(CONFIG_ARM64_LSE_ATOMICS) +#ifdef CONFIG_ARM64_LSE_ATOMICS { .desc = "LSE atomic instructions", .capability = ARM64_HAS_LSE_ATOMICS, @@ -1302,7 +1382,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .sign = FTR_UNSIGNED, .min_field_value = 2, }, -#endif /* CONFIG_AS_LSE && CONFIG_ARM64_LSE_ATOMICS */ +#endif /* CONFIG_ARM64_LSE_ATOMICS */ { .desc = "Software prefetching using PRFM", .capability = ARM64_HAS_NO_HW_PREFETCH, @@ -1368,7 +1448,7 @@ static const struct arm64_cpu_capabilities arm64_features[] = { { /* FP/SIMD is not implemented */ .capability = ARM64_HAS_NO_FPSIMD, - .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .type = ARM64_CPUCAP_BOOT_RESTRICTED_CPU_LOCAL_FEATURE, .min_field_value = 0, .matches = has_no_fpsimd, }, @@ -1567,6 +1647,31 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .min_field_value = 1, }, #endif +#ifdef CONFIG_ARM64_E0PD + { + .desc = "E0PD", + .capability = ARM64_HAS_E0PD, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .sys_reg = SYS_ID_AA64MMFR2_EL1, + .sign = FTR_UNSIGNED, + .field_pos = ID_AA64MMFR2_E0PD_SHIFT, + .matches = has_cpuid_feature, + .min_field_value = 1, + .cpu_enable = cpu_enable_e0pd, + }, +#endif +#ifdef CONFIG_ARCH_RANDOM + { + .desc = "Random Number Generator", + .capability = ARM64_HAS_RNG, + .type = ARM64_CPUCAP_SYSTEM_FEATURE, + .matches = has_cpuid_feature, + .sys_reg = SYS_ID_AA64ISAR0_EL1, + .field_pos = ID_AA64ISAR0_RNDR_SHIFT, + .sign = FTR_UNSIGNED, + .min_field_value = 1, + }, +#endif {}, }; @@ -1596,6 +1701,12 @@ static const struct arm64_cpu_capabilities arm64_features[] = { .match_list = list, \ } +#define HWCAP_CAP_MATCH(match, cap_type, cap) \ + { \ + __HWCAP_CAP(#cap, cap_type, cap) \ + .matches = match, \ + } + #ifdef CONFIG_ARM64_PTR_AUTH static const struct arm64_cpu_capabilities ptr_auth_hwcap_addr_matches[] = { { @@ -1638,6 +1749,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RNDR_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_RNG), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), @@ -1651,6 +1763,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FRINTTS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FRINT), HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_SB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SB), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_BF16_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_BF16), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DGH_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DGH), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_I8MM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_I8MM), HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), @@ -1658,8 +1773,12 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BF16_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BF16, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_I8MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_I8MM, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F32MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F32MM, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_F64MM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_F64MM, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM), #endif HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), #ifdef CONFIG_ARM64_PTR_AUTH @@ -1669,8 +1788,35 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { {}, }; +#ifdef CONFIG_COMPAT +static bool compat_has_neon(const struct arm64_cpu_capabilities *cap, int scope) +{ + /* + * Check that all of MVFR1_EL1.{SIMDSP, SIMDInt, SIMDLS} are available, + * in line with that of arm32 as in vfp_init(). We make sure that the + * check is future proof, by making sure value is non-zero. + */ + u32 mvfr1; + + WARN_ON(scope == SCOPE_LOCAL_CPU && preemptible()); + if (scope == SCOPE_SYSTEM) + mvfr1 = read_sanitised_ftr_reg(SYS_MVFR1_EL1); + else + mvfr1 = read_sysreg_s(SYS_MVFR1_EL1); + + return cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDSP_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDINT_SHIFT) && + cpuid_feature_extract_unsigned_field(mvfr1, MVFR1_SIMDLS_SHIFT); +} +#endif + static const struct arm64_cpu_capabilities compat_elf_hwcaps[] = { #ifdef CONFIG_COMPAT + HWCAP_CAP_MATCH(compat_has_neon, CAP_COMPAT_HWCAP, COMPAT_HWCAP_NEON), + HWCAP_CAP(SYS_MVFR1_EL1, MVFR1_SIMDFMAC_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv4), + /* Arm v8 mandates MVFR0.FPDP == {0, 2}. So, piggy back on this for the presence of VFP support */ + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFP), + HWCAP_CAP(SYS_MVFR0_EL1, MVFR0_FPDP_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP, COMPAT_HWCAP_VFPv3), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 2, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_PMULL), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_AES_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_AES), HWCAP_CAP(SYS_ID_ISAR5_EL1, ID_ISAR5_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_COMPAT_HWCAP2, COMPAT_HWCAP2_SHA1), @@ -1974,7 +2120,7 @@ void check_local_cpu_capabilities(void) * Otherwise, this CPU should verify that it has all the system * advertised capabilities. */ - if (!sys_caps_initialised) + if (!system_capabilities_finalized()) update_cpu_capabilities(SCOPE_LOCAL_CPU); else verify_local_cpu_capabilities(); @@ -1988,14 +2134,6 @@ static void __init setup_boot_cpu_capabilities(void) enable_cpu_capabilities(SCOPE_BOOT_CPU); } -DEFINE_STATIC_KEY_FALSE(arm64_const_caps_ready); -EXPORT_SYMBOL(arm64_const_caps_ready); - -static void __init mark_const_caps_ready(void) -{ - static_branch_enable(&arm64_const_caps_ready); -} - bool this_cpu_has_cap(unsigned int n) { if (!WARN_ON(preemptible()) && n < ARM64_NCAPS) { @@ -2054,7 +2192,6 @@ void __init setup_cpu_features(void) u32 cwg; setup_system_capabilities(); - mark_const_caps_ready(); setup_elf_hwcaps(arm64_elf_hwcaps); if (system_supports_32bit_el0()) @@ -2067,7 +2204,7 @@ void __init setup_cpu_features(void) minsigstksz_setup(); /* Advertise that we have computed the system capabilities */ - set_sys_caps_initialised(); + finalize_system_capabilities(); /* * Check for sane CTR_EL0.CWG value. diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 56bba746da1c..86136075ae41 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -84,6 +84,14 @@ static const char *const hwcap_str[] = { "svesm4", "flagm2", "frint", + "svei8mm", + "svef32mm", + "svef64mm", + "svebf16", + "i8mm", + "bf16", + "dgh", + "rng", NULL }; @@ -360,6 +368,7 @@ static void __cpuinfo_store_cpu(struct cpuinfo_arm64 *info) info->reg_id_isar3 = read_cpuid(ID_ISAR3_EL1); info->reg_id_isar4 = read_cpuid(ID_ISAR4_EL1); info->reg_id_isar5 = read_cpuid(ID_ISAR5_EL1); + info->reg_id_isar6 = read_cpuid(ID_ISAR6_EL1); info->reg_id_mmfr0 = read_cpuid(ID_MMFR0_EL1); info->reg_id_mmfr1 = read_cpuid(ID_MMFR1_EL1); info->reg_id_mmfr2 = read_cpuid(ID_MMFR2_EL1); diff --git a/arch/arm64/kernel/entry-common.c b/arch/arm64/kernel/entry-common.c index 5dce5e56995a..fde59981445c 100644 --- a/arch/arm64/kernel/entry-common.c +++ b/arch/arm64/kernel/entry-common.c @@ -36,14 +36,14 @@ static void notrace el1_pc(struct pt_regs *regs, unsigned long esr) } NOKPROBE_SYMBOL(el1_pc); -static void el1_undef(struct pt_regs *regs) +static void notrace el1_undef(struct pt_regs *regs) { local_daif_inherit(regs); do_undefinstr(regs); } NOKPROBE_SYMBOL(el1_undef); -static void el1_inv(struct pt_regs *regs, unsigned long esr) +static void notrace el1_inv(struct pt_regs *regs, unsigned long esr) { local_daif_inherit(regs); bad_mode(regs, 0, esr); @@ -215,7 +215,7 @@ static void notrace el0_svc(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - el0_svc_handler(regs); + do_el0_svc(regs); } NOKPROBE_SYMBOL(el0_svc); @@ -281,7 +281,7 @@ static void notrace el0_svc_compat(struct pt_regs *regs) if (system_uses_irq_prio_masking()) gic_write_pmr(GIC_PRIO_IRQON | GIC_PRIO_PSR_I_SET); - el0_svc_compat_handler(regs); + do_el0_svc_compat(regs); } NOKPROBE_SYMBOL(el0_svc_compat); diff --git a/arch/arm64/kernel/entry.S b/arch/arm64/kernel/entry.S index 7c6a0a41676f..9461d812ae27 100644 --- a/arch/arm64/kernel/entry.S +++ b/arch/arm64/kernel/entry.S @@ -60,16 +60,16 @@ .macro kernel_ventry, el, label, regsize = 64 .align 7 #ifdef CONFIG_UNMAP_KERNEL_AT_EL0 -alternative_if ARM64_UNMAP_KERNEL_AT_EL0 .if \el == 0 +alternative_if ARM64_UNMAP_KERNEL_AT_EL0 .if \regsize == 64 mrs x30, tpidrro_el0 msr tpidrro_el0, xzr .else mov x30, xzr .endif - .endif alternative_else_nop_endif + .endif #endif sub sp, sp, #S_FRAME_SIZE @@ -167,9 +167,13 @@ alternative_cb_end .if \el == 0 clear_gp_regs mrs x21, sp_el0 - ldr_this_cpu tsk, __entry_task, x20 // Ensure MDSCR_EL1.SS is clear, - ldr x19, [tsk, #TSK_TI_FLAGS] // since we can unmask debug - disable_step_tsk x19, x20 // exceptions when scheduling. + ldr_this_cpu tsk, __entry_task, x20 + msr sp_el0, tsk + + // Ensure MDSCR_EL1.SS is clear, since we can unmask debug exceptions + // when scheduling. + ldr x19, [tsk, #TSK_TI_FLAGS] + disable_step_tsk x19, x20 apply_ssbd 1, x22, x23 @@ -232,13 +236,6 @@ alternative_else_nop_endif str w21, [sp, #S_SYSCALLNO] .endif - /* - * Set sp_el0 to current thread_info. - */ - .if \el == 0 - msr sp_el0, tsk - .endif - /* Save pmr */ alternative_if ARM64_HAS_IRQ_PRIO_MASKING mrs_s x20, SYS_ICC_PMR_EL1 @@ -605,7 +602,7 @@ el1_irq: irq_handler -#ifdef CONFIG_PREEMPT +#ifdef CONFIG_PREEMPTION ldr x24, [tsk, #TSK_TI_PREEMPT] // get preempt count alternative_if ARM64_HAS_IRQ_PRIO_MASKING /* @@ -653,6 +650,7 @@ el0_sync: mov x0, sp bl el0_sync_handler b ret_to_user +ENDPROC(el0_sync) #ifdef CONFIG_COMPAT .align 6 @@ -661,16 +659,18 @@ el0_sync_compat: mov x0, sp bl el0_sync_compat_handler b ret_to_user -ENDPROC(el0_sync) +ENDPROC(el0_sync_compat) .align 6 el0_irq_compat: kernel_entry 0, 32 b el0_irq_naked +ENDPROC(el0_irq_compat) el0_error_compat: kernel_entry 0, 32 b el0_error_naked +ENDPROC(el0_error_compat) #endif .align 6 diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index 3eb338f14386..94289d126993 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -269,6 +269,7 @@ static void sve_free(struct task_struct *task) */ static void task_fpsimd_load(void) { + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); if (system_supports_sve() && test_thread_flag(TIF_SVE)) @@ -289,6 +290,7 @@ static void fpsimd_save(void) this_cpu_ptr(&fpsimd_last_state); /* set by fpsimd_bind_task_to_cpu() or fpsimd_bind_state_to_cpu() */ + WARN_ON(!system_supports_fpsimd()); WARN_ON(!have_cpu_fpsimd_context()); if (!test_thread_flag(TIF_FOREIGN_FPSTATE)) { @@ -1092,6 +1094,7 @@ void fpsimd_bind_task_to_cpu(void) struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); + WARN_ON(!system_supports_fpsimd()); last->st = ¤t->thread.uw.fpsimd_state; last->sve_state = current->thread.sve_state; last->sve_vl = current->thread.sve_vl; @@ -1114,6 +1117,7 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, struct fpsimd_last_state_struct *last = this_cpu_ptr(&fpsimd_last_state); + WARN_ON(!system_supports_fpsimd()); WARN_ON(!in_softirq() && !irqs_disabled()); last->st = st; @@ -1128,8 +1132,19 @@ void fpsimd_bind_state_to_cpu(struct user_fpsimd_state *st, void *sve_state, */ void fpsimd_restore_current_state(void) { - if (!system_supports_fpsimd()) + /* + * For the tasks that were created before we detected the absence of + * FP/SIMD, the TIF_FOREIGN_FPSTATE could be set via fpsimd_thread_switch(), + * e.g, init. This could be then inherited by the children processes. + * If we later detect that the system doesn't support FP/SIMD, + * we must clear the flag for all the tasks to indicate that the + * FPSTATE is clean (as we can't have one) to avoid looping for ever in + * do_notify_resume(). + */ + if (!system_supports_fpsimd()) { + clear_thread_flag(TIF_FOREIGN_FPSTATE); return; + } get_cpu_fpsimd_context(); @@ -1148,7 +1163,7 @@ void fpsimd_restore_current_state(void) */ void fpsimd_update_current_state(struct user_fpsimd_state const *state) { - if (!system_supports_fpsimd()) + if (WARN_ON(!system_supports_fpsimd())) return; get_cpu_fpsimd_context(); @@ -1179,7 +1194,13 @@ void fpsimd_update_current_state(struct user_fpsimd_state const *state) void fpsimd_flush_task_state(struct task_struct *t) { t->thread.fpsimd_cpu = NR_CPUS; - + /* + * If we don't support fpsimd, bail out after we have + * reset the fpsimd_cpu for this task and clear the + * FPSTATE. + */ + if (!system_supports_fpsimd()) + return; barrier(); set_tsk_thread_flag(t, TIF_FOREIGN_FPSTATE); @@ -1193,6 +1214,7 @@ void fpsimd_flush_task_state(struct task_struct *t) */ static void fpsimd_flush_cpu_state(void) { + WARN_ON(!system_supports_fpsimd()); __this_cpu_write(fpsimd_last_state.st, NULL); set_thread_flag(TIF_FOREIGN_FPSTATE); } @@ -1203,6 +1225,8 @@ static void fpsimd_flush_cpu_state(void) */ void fpsimd_save_and_flush_cpu_state(void) { + if (!system_supports_fpsimd()) + return; WARN_ON(preemptible()); __get_cpu_fpsimd_context(); fpsimd_save(); diff --git a/arch/arm64/kernel/hibernate.c b/arch/arm64/kernel/hibernate.c index a96b2921d22c..590963c9c609 100644 --- a/arch/arm64/kernel/hibernate.c +++ b/arch/arm64/kernel/hibernate.c @@ -182,78 +182,79 @@ int arch_hibernation_header_restore(void *addr) } EXPORT_SYMBOL(arch_hibernation_header_restore); -/* - * Copies length bytes, starting at src_start into an new page, - * perform cache maintentance, then maps it at the specified address low - * address as executable. - * - * This is used by hibernate to copy the code it needs to execute when - * overwriting the kernel text. This function generates a new set of page - * tables, which it loads into ttbr0. - * - * Length is provided as we probably only want 4K of data, even on a 64K - * page system. - */ -static int create_safe_exec_page(void *src_start, size_t length, - unsigned long dst_addr, - phys_addr_t *phys_dst_addr, - void *(*allocator)(gfp_t mask), - gfp_t mask) +static int trans_pgd_map_page(pgd_t *trans_pgd, void *page, + unsigned long dst_addr, + pgprot_t pgprot) { - int rc = 0; - pgd_t *trans_pgd; pgd_t *pgdp; pud_t *pudp; pmd_t *pmdp; pte_t *ptep; - unsigned long dst = (unsigned long)allocator(mask); - - if (!dst) { - rc = -ENOMEM; - goto out; - } - - memcpy((void *)dst, src_start, length); - __flush_icache_range(dst, dst + length); - - trans_pgd = allocator(mask); - if (!trans_pgd) { - rc = -ENOMEM; - goto out; - } pgdp = pgd_offset_raw(trans_pgd, dst_addr); if (pgd_none(READ_ONCE(*pgdp))) { - pudp = allocator(mask); - if (!pudp) { - rc = -ENOMEM; - goto out; - } + pudp = (void *)get_safe_page(GFP_ATOMIC); + if (!pudp) + return -ENOMEM; pgd_populate(&init_mm, pgdp, pudp); } pudp = pud_offset(pgdp, dst_addr); if (pud_none(READ_ONCE(*pudp))) { - pmdp = allocator(mask); - if (!pmdp) { - rc = -ENOMEM; - goto out; - } + pmdp = (void *)get_safe_page(GFP_ATOMIC); + if (!pmdp) + return -ENOMEM; pud_populate(&init_mm, pudp, pmdp); } pmdp = pmd_offset(pudp, dst_addr); if (pmd_none(READ_ONCE(*pmdp))) { - ptep = allocator(mask); - if (!ptep) { - rc = -ENOMEM; - goto out; - } + ptep = (void *)get_safe_page(GFP_ATOMIC); + if (!ptep) + return -ENOMEM; pmd_populate_kernel(&init_mm, pmdp, ptep); } ptep = pte_offset_kernel(pmdp, dst_addr); - set_pte(ptep, pfn_pte(virt_to_pfn(dst), PAGE_KERNEL_EXEC)); + set_pte(ptep, pfn_pte(virt_to_pfn(page), PAGE_KERNEL_EXEC)); + + return 0; +} + +/* + * Copies length bytes, starting at src_start into an new page, + * perform cache maintenance, then maps it at the specified address low + * address as executable. + * + * This is used by hibernate to copy the code it needs to execute when + * overwriting the kernel text. This function generates a new set of page + * tables, which it loads into ttbr0. + * + * Length is provided as we probably only want 4K of data, even on a 64K + * page system. + */ +static int create_safe_exec_page(void *src_start, size_t length, + unsigned long dst_addr, + phys_addr_t *phys_dst_addr) +{ + void *page = (void *)get_safe_page(GFP_ATOMIC); + pgd_t *trans_pgd; + int rc; + + if (!page) + return -ENOMEM; + + memcpy(page, src_start, length); + __flush_icache_range((unsigned long)page, (unsigned long)page + length); + + trans_pgd = (void *)get_safe_page(GFP_ATOMIC); + if (!trans_pgd) + return -ENOMEM; + + rc = trans_pgd_map_page(trans_pgd, page, dst_addr, + PAGE_KERNEL_EXEC); + if (rc) + return rc; /* * Load our new page tables. A strict BBM approach requires that we @@ -269,13 +270,12 @@ static int create_safe_exec_page(void *src_start, size_t length, */ cpu_set_reserved_ttbr0(); local_flush_tlb_all(); - write_sysreg(phys_to_ttbr(virt_to_phys(pgdp)), ttbr0_el1); + write_sysreg(phys_to_ttbr(virt_to_phys(trans_pgd)), ttbr0_el1); isb(); - *phys_dst_addr = virt_to_phys((void *)dst); + *phys_dst_addr = virt_to_phys(page); -out: - return rc; + return 0; } #define dcache_clean_range(start, end) __flush_dcache_area(start, (end - start)) @@ -450,7 +450,7 @@ static int copy_pud(pgd_t *dst_pgdp, pgd_t *src_pgdp, unsigned long start, return -ENOMEM; } else { set_pud(dst_pudp, - __pud(pud_val(pud) & ~PMD_SECT_RDONLY)); + __pud(pud_val(pud) & ~PUD_SECT_RDONLY)); } } while (dst_pudp++, src_pudp++, addr = next, addr != end); @@ -476,6 +476,24 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, return 0; } +static int trans_pgd_create_copy(pgd_t **dst_pgdp, unsigned long start, + unsigned long end) +{ + int rc; + pgd_t *trans_pgd = (pgd_t *)get_safe_page(GFP_ATOMIC); + + if (!trans_pgd) { + pr_err("Failed to allocate memory for temporary page tables.\n"); + return -ENOMEM; + } + + rc = copy_page_tables(trans_pgd, start, end); + if (!rc) + *dst_pgdp = trans_pgd; + + return rc; +} + /* * Setup then Resume from the hibernate image using swsusp_arch_suspend_exit(). * @@ -484,7 +502,7 @@ static int copy_page_tables(pgd_t *dst_pgdp, unsigned long start, */ int swsusp_arch_resume(void) { - int rc = 0; + int rc; void *zero_page; size_t exit_size; pgd_t *tmp_pg_dir; @@ -497,15 +515,9 @@ int swsusp_arch_resume(void) * Create a second copy of just the linear map, and use this when * restoring. */ - tmp_pg_dir = (pgd_t *)get_safe_page(GFP_ATOMIC); - if (!tmp_pg_dir) { - pr_err("Failed to allocate memory for temporary page tables.\n"); - rc = -ENOMEM; - goto out; - } - rc = copy_page_tables(tmp_pg_dir, PAGE_OFFSET, PAGE_END); + rc = trans_pgd_create_copy(&tmp_pg_dir, PAGE_OFFSET, PAGE_END); if (rc) - goto out; + return rc; /* * We need a zero page that is zero before & after resume in order to @@ -514,8 +526,7 @@ int swsusp_arch_resume(void) zero_page = (void *)get_safe_page(GFP_ATOMIC); if (!zero_page) { pr_err("Failed to allocate zero page.\n"); - rc = -ENOMEM; - goto out; + return -ENOMEM; } /* @@ -530,11 +541,10 @@ int swsusp_arch_resume(void) */ rc = create_safe_exec_page(__hibernate_exit_text_start, exit_size, (unsigned long)hibernate_exit, - &phys_hibernate_exit, - (void *)get_safe_page, GFP_ATOMIC); + &phys_hibernate_exit); if (rc) { pr_err("Failed to create safe executable page for hibernate_exit code.\n"); - goto out; + return rc; } /* @@ -561,8 +571,7 @@ int swsusp_arch_resume(void) resume_hdr.reenter_kernel, restore_pblist, resume_hdr.__hyp_stub_vectors, virt_to_phys(zero_page)); -out: - return rc; + return 0; } int hibernate_resume_nonboot_cpu_disable(void) diff --git a/arch/arm64/kernel/kaslr.c b/arch/arm64/kernel/kaslr.c index 2a11a962e571..53b8a4ee64ff 100644 --- a/arch/arm64/kernel/kaslr.c +++ b/arch/arm64/kernel/kaslr.c @@ -120,6 +120,17 @@ u64 __init kaslr_early_init(u64 dt_phys) return 0; } + /* + * Mix in any entropy obtainable architecturally, open coded + * since this runs extremely early. + */ + if (__early_cpu_has_rndr()) { + unsigned long raw; + + if (__arm64_rndr(&raw)) + seed ^= raw; + } + if (!seed) { kaslr_status = KASLR_DISABLED_NO_SEED; return 0; diff --git a/arch/arm64/kernel/kexec_image.c b/arch/arm64/kernel/kexec_image.c index 29a9428486a5..af9987c154ca 100644 --- a/arch/arm64/kernel/kexec_image.c +++ b/arch/arm64/kernel/kexec_image.c @@ -47,10 +47,6 @@ static void *image_load(struct kimage *image, struct kexec_segment *kernel_segment; int ret; - /* We don't support crash kernels yet. */ - if (image->type == KEXEC_TYPE_CRASH) - return ERR_PTR(-EOPNOTSUPP); - /* * We require a kernel with an unambiguous Image header. Per * Documentation/arm64/booting.rst, this is the case when image_size diff --git a/arch/arm64/kernel/machine_kexec.c b/arch/arm64/kernel/machine_kexec.c index 0df8493624e0..8e9c924423b4 100644 --- a/arch/arm64/kernel/machine_kexec.c +++ b/arch/arm64/kernel/machine_kexec.c @@ -160,18 +160,6 @@ void machine_kexec(struct kimage *kimage) kexec_image_info(kimage); - pr_debug("%s:%d: control_code_page: %p\n", __func__, __LINE__, - kimage->control_code_page); - pr_debug("%s:%d: reboot_code_buffer_phys: %pa\n", __func__, __LINE__, - &reboot_code_buffer_phys); - pr_debug("%s:%d: reboot_code_buffer: %p\n", __func__, __LINE__, - reboot_code_buffer); - pr_debug("%s:%d: relocate_new_kernel: %p\n", __func__, __LINE__, - arm64_relocate_new_kernel); - pr_debug("%s:%d: relocate_new_kernel_size: 0x%lx(%lu) bytes\n", - __func__, __LINE__, arm64_relocate_new_kernel_size, - arm64_relocate_new_kernel_size); - /* * Copy arm64_relocate_new_kernel to the reboot_code_buffer for use * after the kernel is shut down. diff --git a/arch/arm64/kernel/machine_kexec_file.c b/arch/arm64/kernel/machine_kexec_file.c index 7b08bf9499b6..dd3ae8081b38 100644 --- a/arch/arm64/kernel/machine_kexec_file.c +++ b/arch/arm64/kernel/machine_kexec_file.c @@ -17,12 +17,15 @@ #include <linux/memblock.h> #include <linux/of_fdt.h> #include <linux/random.h> +#include <linux/slab.h> #include <linux/string.h> #include <linux/types.h> #include <linux/vmalloc.h> #include <asm/byteorder.h> /* relevant device tree properties */ +#define FDT_PROP_KEXEC_ELFHDR "linux,elfcorehdr" +#define FDT_PROP_MEM_RANGE "linux,usable-memory-range" #define FDT_PROP_INITRD_START "linux,initrd-start" #define FDT_PROP_INITRD_END "linux,initrd-end" #define FDT_PROP_BOOTARGS "bootargs" @@ -40,6 +43,10 @@ int arch_kimage_file_post_load_cleanup(struct kimage *image) vfree(image->arch.dtb); image->arch.dtb = NULL; + vfree(image->arch.elf_headers); + image->arch.elf_headers = NULL; + image->arch.elf_headers_sz = 0; + return kexec_image_post_load_cleanup_default(image); } @@ -55,6 +62,31 @@ static int setup_dtb(struct kimage *image, off = ret; + ret = fdt_delprop(dtb, off, FDT_PROP_KEXEC_ELFHDR); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + ret = fdt_delprop(dtb, off, FDT_PROP_MEM_RANGE); + if (ret && ret != -FDT_ERR_NOTFOUND) + goto out; + + if (image->type == KEXEC_TYPE_CRASH) { + /* add linux,elfcorehdr */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_KEXEC_ELFHDR, + image->arch.elf_headers_mem, + image->arch.elf_headers_sz); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + + /* add linux,usable-memory-range */ + ret = fdt_appendprop_addrrange(dtb, 0, off, + FDT_PROP_MEM_RANGE, + crashk_res.start, + crashk_res.end - crashk_res.start + 1); + if (ret) + return (ret == -FDT_ERR_NOSPACE ? -ENOMEM : -EINVAL); + } + /* add bootargs */ if (cmdline) { ret = fdt_setprop_string(dtb, off, FDT_PROP_BOOTARGS, cmdline); @@ -125,8 +157,8 @@ out: } /* - * More space needed so that we can add initrd, bootargs, kaslr-seed, and - * rng-seed. + * More space needed so that we can add initrd, bootargs, kaslr-seed, + * rng-seed, userable-memory-range and elfcorehdr. */ #define DTB_EXTRA_SPACE 0x1000 @@ -174,6 +206,43 @@ static int create_dtb(struct kimage *image, } } +static int prepare_elf_headers(void **addr, unsigned long *sz) +{ + struct crash_mem *cmem; + unsigned int nr_ranges; + int ret; + u64 i; + phys_addr_t start, end; + + nr_ranges = 1; /* for exclusion of crashkernel region */ + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) + nr_ranges++; + + cmem = kmalloc(sizeof(struct crash_mem) + + sizeof(struct crash_mem_range) * nr_ranges, GFP_KERNEL); + if (!cmem) + return -ENOMEM; + + cmem->max_nr_ranges = nr_ranges; + cmem->nr_ranges = 0; + for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, + MEMBLOCK_NONE, &start, &end, NULL) { + cmem->ranges[cmem->nr_ranges].start = start; + cmem->ranges[cmem->nr_ranges].end = end - 1; + cmem->nr_ranges++; + } + + /* Exclude crashkernel region */ + ret = crash_exclude_mem_range(cmem, crashk_res.start, crashk_res.end); + + if (!ret) + ret = crash_prepare_elf64_headers(cmem, true, addr, sz); + + kfree(cmem); + return ret; +} + int load_other_segments(struct kimage *image, unsigned long kernel_load_addr, unsigned long kernel_size, @@ -181,14 +250,43 @@ int load_other_segments(struct kimage *image, char *cmdline) { struct kexec_buf kbuf; - void *dtb = NULL; - unsigned long initrd_load_addr = 0, dtb_len; + void *headers, *dtb = NULL; + unsigned long headers_sz, initrd_load_addr = 0, dtb_len; int ret = 0; kbuf.image = image; /* not allocate anything below the kernel */ kbuf.buf_min = kernel_load_addr + kernel_size; + /* load elf core header */ + if (image->type == KEXEC_TYPE_CRASH) { + ret = prepare_elf_headers(&headers, &headers_sz); + if (ret) { + pr_err("Preparing elf core header failed\n"); + goto out_err; + } + + kbuf.buffer = headers; + kbuf.bufsz = headers_sz; + kbuf.mem = KEXEC_BUF_MEM_UNKNOWN; + kbuf.memsz = headers_sz; + kbuf.buf_align = SZ_64K; /* largest supported page size */ + kbuf.buf_max = ULONG_MAX; + kbuf.top_down = true; + + ret = kexec_add_buffer(&kbuf); + if (ret) { + vfree(headers); + goto out_err; + } + image->arch.elf_headers = headers; + image->arch.elf_headers_mem = kbuf.mem; + image->arch.elf_headers_sz = headers_sz; + + pr_debug("Loaded elf core header at 0x%lx bufsz=0x%lx memsz=0x%lx\n", + image->arch.elf_headers_mem, headers_sz, headers_sz); + } + /* load initrd */ if (initrd) { kbuf.buffer = initrd; diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c index 71f788cd2b18..bbb0f0c145f6 100644 --- a/arch/arm64/kernel/process.c +++ b/arch/arm64/kernel/process.c @@ -360,8 +360,8 @@ int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src) asmlinkage void ret_from_fork(void) asm("ret_from_fork"); -int copy_thread(unsigned long clone_flags, unsigned long stack_start, - unsigned long stk_sz, struct task_struct *p) +int copy_thread_tls(unsigned long clone_flags, unsigned long stack_start, + unsigned long stk_sz, struct task_struct *p, unsigned long tls) { struct pt_regs *childregs = task_pt_regs(p); @@ -394,11 +394,11 @@ int copy_thread(unsigned long clone_flags, unsigned long stack_start, } /* - * If a TLS pointer was passed to clone (4th argument), use it - * for the new thread. + * If a TLS pointer was passed to clone, use it for the new + * thread. */ if (clone_flags & CLONE_SETTLS) - p->thread.uw.tp_value = childregs->regs[3]; + p->thread.uw.tp_value = tls; } else { memset(childregs, 0, sizeof(struct pt_regs)); childregs->pstate = PSR_MODE_EL1h; @@ -646,6 +646,6 @@ asmlinkage void __sched arm64_preempt_schedule_irq(void) * Only allow a task to be preempted once cpufeatures have been * enabled. */ - if (static_branch_likely(&arm64_const_caps_ready)) + if (system_capabilities_finalized()) preempt_schedule_irq(); } diff --git a/arch/arm64/kernel/ptrace.c b/arch/arm64/kernel/ptrace.c index 6771c399d40c..cd6e5fa48b9c 100644 --- a/arch/arm64/kernel/ptrace.c +++ b/arch/arm64/kernel/ptrace.c @@ -615,6 +615,13 @@ static int gpr_set(struct task_struct *target, const struct user_regset *regset, return 0; } +static int fpr_active(struct task_struct *target, const struct user_regset *regset) +{ + if (!system_supports_fpsimd()) + return -ENODEV; + return regset->n; +} + /* * TODO: update fp accessors for lazy context switching (sync/flush hwstate) */ @@ -637,6 +644,9 @@ static int fpr_get(struct task_struct *target, const struct user_regset *regset, unsigned int pos, unsigned int count, void *kbuf, void __user *ubuf) { + if (!system_supports_fpsimd()) + return -EINVAL; + if (target == current) fpsimd_preserve_current_state(); @@ -676,6 +686,9 @@ static int fpr_set(struct task_struct *target, const struct user_regset *regset, { int ret; + if (!system_supports_fpsimd()) + return -EINVAL; + ret = __fpr_set(target, regset, pos, count, kbuf, ubuf, 0); if (ret) return ret; @@ -1134,6 +1147,7 @@ static const struct user_regset aarch64_regsets[] = { */ .size = sizeof(u32), .align = sizeof(u32), + .active = fpr_active, .get = fpr_get, .set = fpr_set }, @@ -1348,6 +1362,9 @@ static int compat_vfp_get(struct task_struct *target, compat_ulong_t fpscr; int ret, vregs_end_pos; + if (!system_supports_fpsimd()) + return -EINVAL; + uregs = &target->thread.uw.fpsimd_state; if (target == current) @@ -1381,6 +1398,9 @@ static int compat_vfp_set(struct task_struct *target, compat_ulong_t fpscr; int ret, vregs_end_pos; + if (!system_supports_fpsimd()) + return -EINVAL; + uregs = &target->thread.uw.fpsimd_state; vregs_end_pos = VFP_STATE_SIZE - sizeof(compat_ulong_t); @@ -1438,6 +1458,7 @@ static const struct user_regset aarch32_regsets[] = { .n = VFP_STATE_SIZE / sizeof(compat_ulong_t), .size = sizeof(compat_ulong_t), .align = sizeof(compat_ulong_t), + .active = fpr_active, .get = compat_vfp_get, .set = compat_vfp_set }, diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c index 56f664561754..a34890bf309f 100644 --- a/arch/arm64/kernel/setup.c +++ b/arch/arm64/kernel/setup.c @@ -285,6 +285,13 @@ void __init setup_arch(char **cmdline_p) *cmdline_p = boot_command_line; + /* + * If know now we are going to need KPTI then use non-global + * mappings from the start, avoiding the cost of rewriting + * everything later. + */ + arm64_use_ng_mappings = kaslr_requires_kpti(); + early_fixmap_init(); early_ioremap_init(); @@ -353,9 +360,6 @@ void __init setup_arch(char **cmdline_p) init_task.thread_info.ttbr0 = __pa_symbol(empty_zero_page); #endif -#ifdef CONFIG_VT - conswitchp = &dummy_con; -#endif if (boot_args[1] || boot_args[2] || boot_args[3]) { pr_err("WARNING: x1-x3 nonzero in violation of boot protocol:\n" "\tx1: %016llx\n\tx2: %016llx\n\tx3: %016llx\n" diff --git a/arch/arm64/kernel/signal.c b/arch/arm64/kernel/signal.c index dd2cdc0d5be2..339882db5a91 100644 --- a/arch/arm64/kernel/signal.c +++ b/arch/arm64/kernel/signal.c @@ -371,6 +371,8 @@ static int parse_user_sigframe(struct user_ctxs *user, goto done; case FPSIMD_MAGIC: + if (!system_supports_fpsimd()) + goto invalid; if (user->fpsimd) goto invalid; @@ -506,7 +508,7 @@ static int restore_sigframe(struct pt_regs *regs, if (err == 0) err = parse_user_sigframe(&user, sf); - if (err == 0) { + if (err == 0 && system_supports_fpsimd()) { if (!user.fpsimd) return -EINVAL; @@ -623,7 +625,7 @@ static int setup_sigframe(struct rt_sigframe_user_layout *user, err |= __copy_to_user(&sf->uc.uc_sigmask, set, sizeof(*set)); - if (err == 0) { + if (err == 0 && system_supports_fpsimd()) { struct fpsimd_context __user *fpsimd_ctx = apply_user_offset(user, user->fpsimd_offset); err |= preserve_fpsimd_context(fpsimd_ctx); diff --git a/arch/arm64/kernel/signal32.c b/arch/arm64/kernel/signal32.c index 12a585386c2f..82feca6f7052 100644 --- a/arch/arm64/kernel/signal32.c +++ b/arch/arm64/kernel/signal32.c @@ -223,7 +223,7 @@ static int compat_restore_sigframe(struct pt_regs *regs, err |= !valid_user_regs(®s->user_regs, current); aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; - if (err == 0) + if (err == 0 && system_supports_fpsimd()) err |= compat_restore_vfp_context(&aux->vfp); return err; @@ -419,7 +419,7 @@ static int compat_setup_sigframe(struct compat_sigframe __user *sf, aux = (struct compat_aux_sigframe __user *) sf->uc.uc_regspace; - if (err == 0) + if (err == 0 && system_supports_fpsimd()) err |= compat_preserve_vfp_context(&aux->vfp); __put_user_error(0, &aux->end_magic, err); diff --git a/arch/arm64/kernel/ssbd.c b/arch/arm64/kernel/ssbd.c index 52cfc6148355..b26955f56750 100644 --- a/arch/arm64/kernel/ssbd.c +++ b/arch/arm64/kernel/ssbd.c @@ -37,7 +37,7 @@ static int ssbd_prctl_set(struct task_struct *task, unsigned long ctrl) /* Unsupported */ if (state == ARM64_SSBD_UNKNOWN) - return -EINVAL; + return -ENODEV; /* Treat the unaffected/mitigated state separately */ if (state == ARM64_SSBD_MITIGATED) { @@ -102,7 +102,7 @@ static int ssbd_prctl_get(struct task_struct *task) { switch (arm64_get_ssbd_state()) { case ARM64_SSBD_UNKNOWN: - return -EINVAL; + return -ENODEV; case ARM64_SSBD_FORCE_ENABLE: return PR_SPEC_DISABLE; case ARM64_SSBD_KERNEL: diff --git a/arch/arm64/kernel/syscall.c b/arch/arm64/kernel/syscall.c index 9a9d98a443fc..a12c0c88d345 100644 --- a/arch/arm64/kernel/syscall.c +++ b/arch/arm64/kernel/syscall.c @@ -154,14 +154,14 @@ static inline void sve_user_discard(void) sve_user_disable(); } -void el0_svc_handler(struct pt_regs *regs) +void do_el0_svc(struct pt_regs *regs) { sve_user_discard(); el0_svc_common(regs, regs->regs[8], __NR_syscalls, sys_call_table); } #ifdef CONFIG_COMPAT -void el0_svc_compat_handler(struct pt_regs *regs) +void do_el0_svc_compat(struct pt_regs *regs) { el0_svc_common(regs, regs->regs[7], __NR_compat_syscalls, compat_sys_call_table); diff --git a/arch/arm64/kernel/traps.c b/arch/arm64/kernel/traps.c index 73caf35c2262..cf402be5c573 100644 --- a/arch/arm64/kernel/traps.c +++ b/arch/arm64/kernel/traps.c @@ -144,9 +144,12 @@ void show_stack(struct task_struct *tsk, unsigned long *sp) #ifdef CONFIG_PREEMPT #define S_PREEMPT " PREEMPT" +#elif defined(CONFIG_PREEMPT_RT) +#define S_PREEMPT " PREEMPT_RT" #else #define S_PREEMPT "" #endif + #define S_SMP " SMP" static int __die(const char *str, int err, struct pt_regs *regs) |